Traian Rebedea

trebedea's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection about 2 hours ago

AIMS: Intent-Aware Safety Classification

Collection

Human-annotated intent dataset and intent-aware safety classifiers (SFT, DPO, distillation, GRPO) for robust LLM guardrails. • 5 items • Updated about 13 hours ago • 3

New activity in nvidia/Nemotron-Content-Safety-Reasoning-4B 4 months ago

multilingual support?

3

#5 opened 5 months ago by

AirAgentSDE

upvoted a paper 5 months ago

Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Models

Paper • 2505.20087 • Published May 26, 2025 • 3

upvoted an article 6 months ago

view article

Article

Nemotron 3 Nano \- A new Standard for Efficient, Open, and Intelligent Agentic Models

• 

nvidia

•

Dec 15, 2025

• 112

New activity in nvidia/Nemotron-Content-Safety-Reasoning-4B 7 months ago

Add subcards

#4 opened 7 months ago by

trebedea

liked a dataset 7 months ago

nvidia/Nemotron-Content-Safety-Reasoning-Dataset

Preview • Updated Nov 26, 2025 • 159 • 11

liked a model 7 months ago

nvidia/Nemotron-Content-Safety-Reasoning-4B

Text Generation • 4B • Updated Dec 6, 2025 • 4.76k • 29

New activity in nvidia/Nemotron-Content-Safety-Reasoning-4B 7 months ago

Added model metadata

#3 opened 7 months ago by

trebedea

upvoted an article 7 months ago

view article

Article

Custom Policy Enforcement with Reasoning: Faster, Safer AI Applications

• 

nvidia

•

Dec 2, 2025

• 26

published an article 7 months ago

view article

Article

Custom Policy Enforcement with Reasoning: Faster, Safer AI Applications

• 

nvidia

•

Dec 2, 2025

• 26

New activity in nvidia/Nemotron-Content-Safety-Reasoning-4B 7 months ago

Update README.md

#2 opened 7 months ago by

trebedea

initial commit

#1 opened 7 months ago by

trebedea

New activity in nvidia/Nemotron-Content-Safety-Reasoning-Dataset 7 months ago

initial commit

#1 opened 7 months ago by

trebedea

upvoted a collection over 1 year ago

NemoGuard

Collection

Essential datasets and models for content safety, topic-following, and security guardrails • 13 items • Updated 12 days ago • 23

liked a model over 1 year ago

nvidia/NemoGuard-JailbreakDetect

Updated Apr 2 • 86 • 24

liked a dataset over 1 year ago

nvidia/CantTalkAboutThis-Topic-Control-Dataset

Viewer • Updated Jan 16, 2025 • 1.09k • 399 • 12

liked 2 models over 1 year ago

nvidia/llama-3.1-nemoguard-8b-content-safety

Text Classification • Updated Jun 9, 2025 • 1.69k • 35

nvidia/llama-3.1-nemoguard-8b-topic-control

Text Classification • Updated Jun 9, 2025 • 2.33k • 18

New activity in OpenLLM-Ro/RoMistral-7b-Instruct-2024-05-17 about 2 years ago

O idee generală cu privire la conținutul folosit pentru antrenare?

4

#1 opened about 2 years ago by

scaraliu

upvoted a paper about 2 years ago

NeMo-Aligner: Scalable Toolkit for Efficient Model Alignment

Paper • 2405.01481 • Published May 2, 2024 • 30